An Adaptive Framework for Simulation and Online Remote Visualization of Critical Climate Applications in Resource-constrained Environments

Abstract

Abstract-Critical climate applications like cyclone tracking and earthquake modeling require high-performance simulations and online visualization simultaneously performed with the simulations for timely analysis. Remote visualization of critical climate events enables joint analysis by geographically distributed climate science community. However, resource constraints including limited storage and slow networks can limit the effectiveness of such online visualization. In this work, we have developed an adaptive framework that simultaneously performs numerical simulations and online remote visualization of critical climate applications in resource-constrained environments. Our framework considers both application and resource dynamics to adapt various application and resource parameters including simulation resolutions, resource configurations and amount of data for visualization. We have developed two algorithms for processor allocation for simulations and the frequency of data for visualization. We show that our optimization method is able to provide about 30% higher simulation rate and consumes about 25-50% lesser storage space than the greedy approach.

A Survey of Interactive Remote Rendering Systems

“…Ciinow [Dharmapurikar 2013a] proposed several bandwidth adaption schemes for different types of data. For cases in which large-scale data is visualized, adaptive streaming should also consider the storage space available on the hard disk as well as network bandwidth [Malakar et al 2010]. …”

Damaris/Viz: A nonintrusive, adaptable and user-friendly in situ visualization framework

“…Malakar et al [21] present an adaptive framework for looselycoupled visualization, in which data is sent over a network to a remote visualization cluster at a frequency that is dynamically adapted depending on resource availability. Our approach also adapts output frequency to resource usage.…”

Visualization for the Physical Sciences

“…Works in the scalable visualization category address I/O, processing and/or visualization challenges caused by large data. Solutions include a remote hardware‐accelerated visualization farm [QMK*06], a public‐resource climate modelling [SFW04], adjusting the frequency of the output from the simulation based on application and resource dynamics [MNV10], using parallel I/O and query‐driven visualization [KGH*09, RPW*08], using parallel I/O [YMW04] and parallel visualization [MSB*03, YMW04] and designing all components of the simulation pipeline (problem description, solver and visualization) so that they execute with shared data structures and no intermediate I/O [TYRG*06]. Fraedrich et al [FSW09] visualize large particle‐based cosmological simulations using a multi‐resolution hierarchy and techniques designed to reduce disk and display limitations produced by the large data.…”

“…We present research to visualize storm and cloud‐scale simulation data [REHL03]*, to visualize warm rain formation and compare weather models with radar observation [SYS*06]*, to analyse air pollution [QCX*07], to visualize the uncertainty associated with weather prediction[SZD*10]*, and to simulate and visualize cyclones[MNV10].…”

“…Malakar et al [MNV10] present an adaptive framework that performs cyclone simulations and remote online visualization as part of a system in which the frequency of the output from the simulation is adjusted based on application and resource dynamics. The goal is to enable continuous progress in the simulation and to maximize temporal resolution in visualization, taking into account limitations in storage and network capacities.…”